team-dev
Executes implementation plans using a persistent team of implementer and reviewers within the current session, with batch-boundary code reviews for quality. Use when you have an implementation plan with independent tasks to execute, need to build or implement a feature from a plan, or the user says "execute the plan", "implement this", "start building", or "team dev". DO NOT TRIGGER when there is no plan yet (use brainstorming first) or when tasks require parallel separate sessions (use executing-plans instead).
88
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that covers all key dimensions well. It provides specific capabilities, natural trigger terms, explicit 'Use when' and 'DO NOT TRIGGER' clauses, and clearly differentiates itself from related skills. The negative trigger conditions are particularly valuable for reducing conflict with adjacent skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple concrete actions: 'executes implementation plans', 'persistent team of implementer and reviewers', 'batch-boundary code reviews'. It also specifies the mechanism (within current session) and quality approach. | 3 / 3 |
Completeness | Clearly answers both 'what' (executes implementation plans using a persistent team with code reviews) and 'when' (explicit 'Use when...' clause with multiple triggers). Also includes helpful 'DO NOT TRIGGER' negative conditions to prevent misuse. | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would say: 'execute the plan', 'implement this', 'start building', 'team dev'. Also includes contextual triggers like 'implementation plan with independent tasks' and 'build or implement a feature from a plan'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit differentiation from related skills: distinguishes itself from brainstorming (no plan yet) and 'executing-plans' (parallel separate sessions). The 'persistent team within current session' framing creates a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured orchestration skill with excellent workflow clarity and progressive disclosure. Its main weaknesses are moderate verbosity (the Graphviz diagrams duplicate prose content and the Red Flags section is extensive) and limited concrete actionability (tool references are named but not shown with executable examples). The skill excels at defining the review feedback loop and error recovery paths.
Suggestions
Replace or remove one of the two Graphviz diagrams — the process diagram largely restates what the prose sections already cover, consuming significant tokens for redundant information.
Add concrete executable examples for key tool invocations (e.g., actual TeamCreate call syntax, SendMessage call syntax) rather than just naming the tools.
Condense the Red Flags section by grouping related items (e.g., combine all review-related red flags into 2-3 consolidated rules instead of 6+ separate bullet points).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes significant verbosity through two large Graphviz diagrams that restate the process described in prose, an extensive 'Red Flags' section with many items that could be condensed, and some redundancy between sections. The dot diagrams add visual structure but consume many tokens for information also conveyed textually. | 2 / 3 |
Actionability | The skill provides a clear process with named tools (TeamCreate, SendMessage) and references to prompt templates, but lacks concrete executable code or commands. The task assignment pattern shows a message template but most guidance is procedural description rather than copy-paste ready commands or API calls. | 2 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced with explicit validation checkpoints: batch-boundary reviews serve as validation gates, there's a clear feedback loop (reviewer finds issues → implementer fixes → re-review → repeat until both approve), and the workflow handles error cases (questions, disagreements, failed reviews) with explicit recovery steps. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, references to external prompt template files (implementer-prompt.md, spec-reviewer-prompt.md, quality-reviewer-prompt.md), and one-level-deep references to related skills (kit:team-orchestration, kit:finish-branch, etc.). The Integration section provides clear navigation to related capabilities. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- shousper/claude-kit
- Commit
a01bac9
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.